基于改进RRT算法的船舶机舱巡检机器人路径规划

Path Planning of Ship Engine Room Inspection Robot Based on Improved RRT Algorithm

针对船舶机舱的复杂环境,以及机舱巡检机器人采用快速扩展随机树(RRT)算法随机扩展节点目的性较差、搜索效率低的问题,提出一种由人工势场引导的RRT算法,根据目标点和障碍物构建人工势场,引导RRT随机树节点扩展,使RRT节点扩展更有目的性,节点数量显著减少。以万箱船舶“COSCO PACIFIC”的机舱底层地图作为机舱机器人运行环境,用MATLAB进行建模仿真,并与RRT算法和BI-RRT算法路径规划进行比较,结果表明:该算法显著提升了机舱机器人路径规划的效率,可更有效的避开障碍物。

In view of the complex environment of the ship’s engine room,and the problem that the engine room patrol robot uses the fast expanding random tree(RRT)algorithm to randomly expand nodes with poor purpose and low search efficiency,a RRT algorithm guided by artificial potential field is proposed.The artificial potential field is constructed according to the target points and obstacles to guide the RRT random tree node expansion,so that the RRT node expansion is more purposeful and the number of nodes is significantly reduced.The engine room bottom map of the 10000-box ship"COSCO PACIFIC"is taken as the operating environment of the engine room robot.The modeling and simulation are carried out with MATLAB,and the path planning is compared with RRT algorithm and BI-RRT algorithm.The results show that the algorithm can significantly improve the efficiency of the engine room robot path planning,and can more effectively avoid the obstacles.